Citations

Abstract Intra-tumor genetic heterogeneity is an important cause of treatment failure of GBM. Using MRI and image-localized biopsies, it is possible to train machine learning (ML) models to predict regional genetic status. However, biopsy samples are limited, making it difficult to train a robust ML model. We proposed a data-inclusive model called Weakly Supervised Ordinal Support Vector Machines (WSO-SVM) which leverages the vast amount of MRI data outside the sparsely sampled biopsy regions to augment the biopsy samples to improve ML accuracy. Our study included a unique dataset of 104 image-localized biopsies with spatially matched multiparametric MRI from 30 untreated Glioblastoma (GBM) patients. Each biopsy sample went through genetic sequencing analysis and our study focused on two GBM hallmark genes, EGFR and PDGFRA. For each gene, a biopsy sample was labeled as “altered” if the copy number of this gene was amplified or a mutation was found, and “non-altered” otherwise. From the localized region of six MRI contrasts from T1gd, T2w, diffusion and perfusion imaging, over 300 texture features were extracted. To account for biopsy sample location uncertainty, six neighboring regions of the biopsy sample including four neighbors two pixels away from the biopsy location and two neighbors on adjacent slices were also included in model training. WSO-SVM achieved 0.83 accuracy, 0.77 sensitivity, and 0.86 specificity for classifying EGFR; 0.77 accuracy, 0.74 sensitivity, and 0.79 specificity for classifying PDGFRA, based on 10-fold cross validation. Furthermore, using the trained models, we generated regional EGFR and PDGFRA alteration maps for each patient within the enhancing and non-enhancing tumoral areas. On average we found a greater proportion of enhancing tumor with co-alteration than non-enhancing tumor, while this trend was reversed when considering only one altered gene. The ratio of EGFR vs PDGFRA alterations was higher in non-enhancing tumor than enhancing tumor.

Abstract INTRODUCTION Glioblastoma (GBM) is a diffusely invasive primary brain tumor with significant spread of tumor cells to the periphery of visible image abnormality. Enhancement of Gadolinium (Gd) contrast agent on magnetic resonance imaging (MRI) has historically been considered a confirmation of local breakdown of the blood brain barrier (BBB) and sufficient drug delivery to the bulk of tumors. In this work, we used GBM-derived xenograft (PDX) models to compare drug delivery in GBM brain for high and low BBB-permeable drugs. MATERIALS AND METHODS Five patient-derived orthotopic xenograft models from two GBM cell lines (GBM39 and GBM12) were co-dosed with erlotinib and osimertinib, two drugs with low and high BBB-permeability, respectively. T1Gd and T2-weighted MRIs were acquired from all animals prior to model sacrifice. Tumors were manually segmented on denoised and standardized MRIs and intensity patterns were captured using first and second order statistical features in the moving 3x3 kernel. We compared drug levels found in Matrix Assisted Laser Desorption Ionization (MALDI) in T1Gd enhancement, T2 enhancement, and normal brain. We also performed linear regression modeling to predict drug levels using MRI features. Model performance was measured using root mean squared error (RMSE). RESULTS Our analysis showed correlations between imaging features and MALDI drug levels. Osimertinib had a uniform distribution across the brain for all animals and all cell lines, consistent with our expectation for a high BBB-penetrant drug. Erlotinib showed the highest drug levels in T2 for GBM39 and in T1Gd for GBM12. Regression models showed promising results for predicting Erlotinib with a low RMSE of 0.037. CONCLUSION Our preliminary results suggest MRI can be predictive of drug levels for low-BBB penetrant drugs. Understanding the relationship between MRIs and drug distribution in diffuse tumors can be beneficial to developing effective treatment.

Abstract Glioblastoma (GBM) is a devastating primary brain tumor known for its heterogeneity with a median survival of 15 months. Clinical imaging remains the primary modality to assess brain tumor response, but it is nearly impossible to distinguish between tumor growth and treatment response. Ki67 is a marker of active cell proliferation that shows inter- and intra-patient heterogeneity and should change under many therapies. In this work, we assessed the utility of a semi-supervised deep learning approach for regionally predicting high-vs-low Ki67 in GBM patients based on MRI. We used both labeled and unlabeled datasets to train the model. Labeled data included 114 MRI-localized biopsies from 43 unique GBM patients with available immunohistochemistry Ki67 labels. Unlabeled data included nine repeat routine pretreatment paired scans of newly-diagnosed GBM patients acquired within three days. Data augmentation techniques were utilized to enhance the size of our data and increase generalizability. Data was split between training, validation, and testing sets using 65-15-20 percent ratios. Model inputs were 16x16x3 patches around biopsies on T1Gd and T2 MRIs for labeled data, and around randomly selected patches inside the T2 abnormal region for unlabeled data. The network was a 4-conv layered VGG-inspired architecture. Training objective was accurate prediction of Ki67 in labeled patches and consistency in predictions across repeat unlabeled patches. We measured final model accuracy on held-out test samples. Our promising preliminary results suggest potential for deep learning in deconvolving the spatial heterogeneity of proliferative GBM subpopulations. If successful, this model can provide a non-invasive readout of cell proliferation and reveal the effectiveness of a given cytotoxic therapy dynamically during the patient's routine follow up. Further, the spatial resolution of our approach provides insights into the intra-tumoral heterogeneity of response which can be related to heterogeneity in localization of therapies (e.g. radiation therapy, drug dose heterogeneity).

Abstract Choosing effective chemotherapies for intravenous delivery to brain tumors is challenging, especially given the protective nature of the blood brain barrier (BBB). Connecting drug distribution to non-invasive, pre-surgical magnetic resonance imaging (MRI) could allow for predictive insight into drug distribution. In a previous study, we found that T2Gd images were predictive of a low BBB penetrant drug (Cefazolin), and FLAIR images were predictive of a high BBB penetrant drug (Levetiracetam). While these results are promising, we further seek to explore how advanced MRI sequences might inform image-based models of drug distribution. Prior to surgery, we acquired advanced dynamic contrast enhanced (DCE) and diffusion weighted imaging (DWI) MRI sequences for eight brain tumor patients (7 gliomas and 1 metastatic adenocarcinoma) in addition to the anatomic MRIs. All resulting quantitative maps and acquired images were co-registered. Prior to incision, patients received injections of cefazolin and levetiracetam. Next, multiple blood samples and biopsies were collected during surgery. Biopsies and plasma samples were analyzed for drug concentration using liquid chromatography mass spectrometry (LCMS), and biopsy drug levels were reported as Brain-Plasma Ratio (BPR). Mean image intensity was extracted from a 15x15 voxel window surrounding the biopsy location. We performed linear regression analyses to determine which combination of images were predictive of BPR. We found that considering quantitative imaging improved our initial ability to predict BPR for both drugs. For cefazolin, the third diffusion tensor eigenvalue (L3) map was significantly correlated with BPR (p< 0.001, R2= 0.36). For levetiracetam, the best model consisted of a combination of images and maps with the L3 map and the isotropic diffusion map (P) being the most influential (p= 0.001, R2= 0.63). Advanced MRI-based modeling is a promising tool for forecasting drug distribution in brain tumors and could be of great importance for understanding efficacy and selecting therapeutic strategies.

OBJECTIVE Recent studies have proposed resection of the T2 FLAIR hyperintensity beyond the T1 contrast enhancement (supramarginal resection [SMR]) for IDH–wild-type glioblastoma (GBM) to further improve patients’ overall survival (OS). GBMs have significant variability in tumor cell density, distribution, and infiltration. Advanced mathematical models based on patient-specific radiographic features have provided new insights into GBM growth kinetics on two important parameters of tumor aggressiveness: proliferation rate (ρ) and diffusion rate (D). The aim of this study was to investigate OS of patients with IDH–wild-type GBM who underwent SMR based on a mathematical model of cell distribution and infiltration profile (tumor invasiveness profile). METHODS Volumetric measurements were obtained from the selected regions of interest from pre- and postoperative MRI studies of included patients. The tumor invasiveness profile (proliferation/diffusion [ρ/D] ratio) was calculated using the following formula: ρ/D ratio = (4π/3) 2/3 × (6.106/[V T2 1/1 − V T1 1/1 ]) 2 , where V T2 and V T1 are the preoperative FLAIR and contrast-enhancing volumes, respectively. Patients were split into subgroups based on their tumor invasiveness profiles. In this analysis, tumors were classified as nodular, moderately diffuse, or highly diffuse. RESULTS A total of 101 patients were included. Tumors were classified as nodular (n = 34), moderately diffuse (n = 34), and highly diffuse (n = 33). On multivariate analysis, increasing SMR had a significant positive correlation with OS for moderately and highly diffuse tumors (HR 0.99, 95% CI 0.98–0.99; p = 0.02; and HR 0.98, 95% CI 0.96–0.99; p = 0.04, respectively). On threshold analysis, OS benefit was seen with SMR from 10% to 29%, 10% to 59%, and 30% to 90%, for nodular, moderately diffuse, and highly diffuse, respectively. CONCLUSIONS The impact of SMR on OS for patients with IDH–wild-type GBM is influenced by the degree of tumor invasiveness. The authors’ results show that increasing SMR is associated with increased OS in patients with moderate and highly diffuse IDH–wild-type GBMs. When grouping SMR into 10% intervals, this benefit was seen for all tumor subgroups, although for nodular tumors, the maximum beneficial SMR percentage was considerably lower than in moderate and highly diffuse tumors.

Abstract Introduction Distinguishing between tumor and treatment effect in post-treatment glioma, although crucial for clinical management, is difficult because contrast-enhancing regions are mixtures of recurrent tumor and reactive tissue, and definitive histopathological criteria do not exist. This study disentangles the marked intra-tumoral heterogeneity in the treatment-recurrent setting by developing an unsupervised framework to algorithmically categorize intraoperative MRI-localized biopsies into three clinically-relevant tissue clusters based on joint analysis of RNA sequencing and histopathological data. Methods A retrospective cohort of 84 MRI-localized biopsies from 37 patients with post-treatment recurrent glioblastoma underwent mRNA extraction and quantification via PLATEseq protocol. For 48 of 84 biopsies, a neighboring piece of tissue underwent quantitative histopathology based on labeling index (LI) for SOX2, CD68, NeuN, Ki67, and H&E. Correlation between LIs and gene expression for these 48 samples was performed. Genes significantly correlated (p<0.05) with ≥1 marker were used for hierarchical clustering of correlation matrix, identifying three mutually-exclusive tissue-specific gene sets. These sets were then used to perform ssGSEA to categorize each of 84 biopsies into one of three tissue types. Results Correlation analysis identified 7779 genes significantly correlated with ≥1 histopathological marker. Clustering revealed three gene sets associated with specific markers: SetA-3688 genes associated with SOX2/Ki67/H&E; SetB-2418 genes associated with CD68; SetC-1673 genes associated with NeuN. ssGSEA using these sets categorized each biopsy into one of three tissue types: 27 biopsies enriched in SetA, 28 in SetB, and 29 in SetC. Conclusions Using MRI-localized biopsies with both RNAseq and histopathological data, this algorithmic approach allows development of three orthogonal tissue-specific gene sets that can be applied to characterize the heterogeneity in post-treatment recurrent glioma: SetA: genes correlated with SOX2/Ki67/H&E, representing recurrent tumor; SetB: genes correlated with CD68 (microglia) representing reactive tissue consistent with treatment effect; SetC: genes correlated with NeuN (neurons), representing infiltrated brain.

Abstract Purpose:Quantify in vivo biomechanical tissue properties in various breast densities and in normal risk and high risk women using Magnetic Resonance Imaging (MRI)/MRE and examine the association between breast biomechanical properties and cancer risk.Methods: Patients with normal risk or high risk of breast cancer underent 3.0 T breast MR imaging and elastography. Breast parenchymal enhancement (BPE), density (from most recent mammogram), stiffness, elasticity, and viscosity were recorded. Within each breast density group (non-dense versus dense), stiffness, elasticity, and viscosity were compared across risk groups (normal versus high). A multivariable logistic regression model was used to evaluate whether the MRE parameters (separately for stiffness, elasticity, and viscosity) predicted risk status after controlling for clinical factors.Results: 50 normal risk and 86 high risk patients were included. Risk groups were similar on age, density, and menopausal status. Among patients with dense breasts, mean stiffness, elasticity, and viscosity were significantly higher in high risk patients (N = 55) compared to normal risk patients (N = 34; all p < 0.001). Stiffness remained a significant predictor of risk status (OR=4.26, 95% CI [1.96, 9.25]) even after controlling for breast density, BPE, age, and menopausal status. Similar results were seen for elasticity and viscosity.Conclusion: A structurally-based, quantitative biomarker of tissue stiffness obtained from MRE is associated with differences in breast cancer risk in dense breasts. Tissue stiffness could provide a novel prognostic marker to help identify high risk women with dense breasts who would benefit from increased surveillance and/or risk reduction measures.

Abstract OBJECTIVE Glioblastoma (GBM) is the most common malignant primary brain tumor in adults, with males more commonly affected than females(1.6:1). Despite advancements in treatments, prognosis is dismal with a median overall survival of 15 months. Our aim was to investigate sex as a variable in GBM patient survival after receiving incremental levels of standard-of-care treatment regimens – different extents of surgical resection and different numbers of cycles of adjuvant temozolomide chemotherapy. METHODS Drawing from our extensive multi-institutional brain tumor repository, we investigated GBM subjects with overall survival (OS), extent of resection (EOR), number of temozolomide (TMZ) cycles, and sex data (n=620, males: n=387, females: n=233). Cox proportional hazard ratios were computed to investigate the multivariable predictive value of the patient variables with OS. Patients were then divided into groups based on their sex, EOR (either biopsy, subtotal resection (STR) or gross total resection (GTR)), and TMZ cycles (I: &lt; 6 cycles, II: 7-11 cycles and III: &gt;12 cycles). RESULTS We observed that STR was beneficial for females (HR=0.52; CI=0.33-0.83; p-value=0.013), while for males the benefit was not detected (HR=0.73; CI=0.46-1.15; p-value=0.173) for STR but was detectable for GTR (HR=0.58, CI=0.37-0.90; p-value=0.014). Females receiving 7-11 cycles of TMZ showed a survival benefit (HR=0.52; CI=0.12-0.53; p-value=0.048) while males in the same group did not (HR=0.74; CI=0.46-1.19; p-value=0.21), in comparison to those in group I of TMZ cycles. No sex differences were identified in patients receiving &lt; =6 cycles or &gt;=12 cycles. CONCLUSION Together, our results contribute to the growing literature that sex differences exist in GBM patients, even in response to standard-of-care therapies. This should be accounted for when designing clinical trials for GBM so that we may advance our pursuit to deliver personalized medicine.

Abstract Glioblastoma (GBM) is the one of the most aggressive and common primary brain malignancies, with a poor median overall survival of less than 15 months. While the immune system is activated and brain-resident microglia and blood-derived macrophages combat the tumor, the tumor can convert some microglia and macrophages to instead exhibit an immune-suppressive phenotype. These co-opted immune cells are thereby termed ‘glioma-associated microglia and macrophages’ (GAMMs), as they allow for continued tumor growth. However, limited clinical data has been collected to understand this phenomenon. As a result, we have collected spatially-distributed image-localized biopsies from a cohort of patients and performed RNA sequencing on each sample. Correlations between normalized RNA counts of genetic markers for macrophages (i.e., CD68, CD163), tumor populations (i.e., SOX2, OLIG2), and key cell functions (i.e., KI67, CASP3) were analyzed. To further investigate the temporal effects that GAMMs have on GBM growth, we proposed the Proliferation-Invasion-Macrophage (PIM) model. This system of partial differential equations incorporates the proliferative and invasive behavior of GBM, as well as populations for both ‘healthy’ and ‘glioma-associated’ macrophages. By exploring the parameter space, we classified the various dynamics of tumor progression and how they relate to the immune response. With further insights of the interactions between GBM and macrophage populations, we can begin to parameterize the model on a patient-specific basis and provide insights to personalized immunotherapies and other novel immune-targeted treatments.